README.md

metadata

metrics:
  - code_eval
library_name: transformers
tags:
  - code
model-index:
  - name: Tiny-StarCoder-Py
    results:
      - task:
          type: text-generation
        dataset:
          type: openai_humaneval
          name: HumanEval
        metrics:
          - name: pass@1
            type: pass@1
            value: 7.84%
            verified: false

TinytarCoderPy

This is a 159M parameters model with teh same architecture as StarCoder (8k context length, MQA & FIM). It was trained on the Python data from StarCoderData for ~6 epochs which amounts to 100B tokens.

Use

Intended use

The model was trained on GitHub code, to assist with some tasks like Assisted Generation. For pure code completion, we advise using our 15B models StarCoder or StarCoderBase.

Generation

# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "bigcode/tiny_pystarcoder"
device = "cuda" # for GPU usage or "cpu" for CPU usage

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))

Fill-in-the-middle

Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:

input_text = "<fim-prefix>def print_hello_world():\n    <fim-suffix>\n    print('Hello world!')<fim-middle>"
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))

Limitations

The model has been trained on source code from 80+ programming languages. The predominant natural language in source code is English although other languages are also present. As such the model is capable of generating code snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits. See the paper for an in-depth discussion of the model limitations.

Training

Model

• Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective
• Pretraining steps: 50k
• Pretraining tokens: 100 billion
• Precision: bfloat16

Hardware

• GPUs: 32 Tesla A100
• Training time: 18 hours

Software

• Orchestration: Megatron-LM
• Neural networks: PyTorch
• BP16 if applicable: apex

License

The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement here.